Agent Skills has structural security weaknesses from missing data-instruction boundaries, single-approval persistent trust, and absent marketplace reviews that require fundamental redesign.
hub
Prompt infection: Llm-to-llm prompt injection within multi-agent systems
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
years
2026 18roles
background 1polarities
support 1representative citing papers
Identifies concrete attacks from a malicious Provider on SAGA and proposes SAGA-BFT, SAGA-MON, SAGA-AUD, and SAGA-HYB mitigations offering different security-performance trade-offs.
FlowSteer is a prompt-only attack that biases multi-agent LLM workflow planning to propagate malicious signals, raising success rates by up to 55%, with FlowGuard as an input-side defense reducing it by up to 34%.
PACT achieves perfect security and utility under oracle provenance by enforcing argument-level trust contracts based on semantic roles and cross-step provenance tracking, outperforming invocation-level monitors in AgentDojo evaluations.
EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.
Autonomous LLM agents can host self-propagating worms via persistent state re-entry, demonstrated with automated analysis tools and blocked by a formal no-propagation defense on three frameworks.
Stage-level tracking of prompt injection reveals that write-node placement and model-specific behaviors determine attack outcomes more than initial exposure in LLM pipelines.
Multi-agent LLM frameworks can spread compromises across agent boundaries via insecure memory inheritance during subagent spawning.
MAGIQ introduces a post-quantum secure system for policy definition, enforcement, and accountability in multi-agent AI using novel cryptographic protocols and UC framework proofs.
ARGUS defends LLM agents from context-aware prompt injections by tracking information provenance and verifying decisions against trustworthy evidence, reducing attack success to 3.8% while retaining 87.5% task utility.
Embedding-based defenses fail against attacks that align malicious message embeddings with benign ones in LLM multi-agent systems, but token-level confidence scores improve robustness by enabling better pruning of suspicious messages.
HDP is a lightweight protocol that binds human authorization to sessions via signed append-only token chains, enabling offline verification of delegation provenance using only an Ed25519 public key and session identifier.
Safety constraints in LLM-based multi-agent systems commonly weaken during execution through memory, communication, and tool use, requiring them to be maintained as explicit state rather than asserted once.
A malicious agent in multi-agent LLM consensus systems can be trained via a surrogate world model and RL to reduce consensus rates and prolong disagreement more effectively than direct prompt attacks.
Researchers developed a fast XGBoost-based detector using 42 runtime features to spot adversarial interaction patterns in LLM agents, running over 9 times faster than LLM detectors on synthetic multi-turn data.
The paper systematizes security for LLM agents in agentic commerce into five threat dimensions, identifies 12 cross-layer attack vectors, and proposes a layered defense architecture.
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.
CASCADE is a cascaded hybrid detector that combines fast regex/entropy filtering, BGE embeddings with local LLM fallback, and output pattern checks to achieve 95.85% precision and 6.06% false-positive rate against prompt injection and related attacks in MCP-based systems.
citing papers explorer
-
Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.